🚀 MERA: Model Evolution and Routing with Skill Adaptation for Agentic Systems at Scale
How can we make small models stronger for on-device agent deployment?
MERA uses stronger models to guide an iterative loop of RL/GRPO, skill learning, and router optimization. Student failures become verified demonstrations, reusable SkillBook procedures, and LoRA updates, helping the small model take on more work over time.
🔥 Results:
Qwen2.5-Coder-1.5B: 28.7% → 49.7% coding pass
Qwen3.5-2B on TAU-2: 14/35 → 18/35
Fine-tuned 2B matches an unadapted 4B model
Don’t just route around small models. Evolve them.
📄
💻
🚀 MERA: Model Evolution and Routing with Skill Adaptation for Agentic Systems at Scale
What if small models could improve themselves, not just be routed around?
MERA evolves both small-model skills and weights, guided by stronger models. Student failures become verified teacher demonstrations, reusable SkillBook procedures, and LoRA updates.
🔥 Results:
Qwen2.5-Coder-1.5B: 28.7% → 49.7% direct pass on coding tasks
Qwen3.5-2B on TAU-2: 14/35 (40.0%) → 18/35 (51.4%)
The adapted 2B model matches an unadapted 4B model
Small models don’t just get routed around.
They get better.
📄 Paper:
💻 Code:
This is not love. This is pressure.
She does daily kalesh and drama, fights with him constantly and creates so much stress that he cannot even work peacefully.
He finally says:
Maine tumhara karja nahi khaya hai, mai nahi karunga shaadi.
Her reply?
Tumko shaadi karni hi padegi.
Tumne mera karja khaya hai.
And now she is asking for his mothers contact too.
Bro is clearly saying NO, but she is acting like his NO does not matter.
Imagine this happening BEFORE marriage.
What do you think happens AFTER marriage?
Shaadi choice honi chahiye, majboori nahi.